Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60611
    Prev
    Next
    INDEX
    Explanations

    business risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COUNT
    -0.08
     tertentu
    -0.08
     معينة
    -0.08
     monta
    -0.08
    лган
    -0.08
    brates
    -0.07
    annel
    -0.07
    _fifo
    -0.07
    COUNT
    -0.07
    aturan
    -0.07
    POSITIVE LOGITS
     adversely
    0.07
     अवसर
    0.07
     hậu
    0.07
     profoundly
    0.07
     aftermath
    0.07
     Amend
    0.07
     bloot
    0.07
    _ICON
    0.07
     poškod
    0.07
     damage
    0.07
    Activations Density 0.005%

    No Known Activations